© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11716
    Prev
    Next
    INDEX
    Explanations

    technical terms and language related to coding and software functionality, specifically focusing on vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saja
    -0.48
     NDEBUG
    -0.47
    șa
    -0.45
    APORE
    -0.45
    atist
    -0.44
    愁
    -0.44
     felice
    -0.42
    gemaakt
    -0.41
    ANOVA
    -0.41
     Lapp
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    1.88
    rungsseite
    1.57
    MigrationBuilder
    1.46
     nahilalakip
    1.44
     beginnetje
    1.44
    ThroughAttribute
    1.41
     pinulongan
    1.38
    featureID
    1.37
    WithIOException
    1.36
     &___
    1.34
    Activations Density 0.752%

    No Known Activations